paper-with-me

홈 › Papers

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training

2024-12-20 · Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Recent advancements highlight the potential of end-to-end real-time spoken dialogue systems, showcasing their low latency and high quality. In this paper, we introduce SLAM-Omni, a timbre-controllable, end-to-end voice interaction system with single-stage training. SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens and decoupling speaker information to a vocoder. By predicting grouped speech semantic tokens at each step, our method significantly reduces the sequence length of audio tokens, accelerating both training and inference. Additionally, we propose historical text prompting to compress dialogue history, facilitating efficient multi-round interactions. Comprehensive evaluations reveal that SLAM-Omni outperforms prior models of similar scale, requiring only 15 hours of training on 4 GPUs with limited data. Notably, it is the first spoken dialogue system to achieve competitive performance with a single-stage training approach, eliminating the need for pre-training on TTS or ASR tasks. Further experiments validate its multilingual and multi-turn dialogue capabilities on larger datasets.

📄 PDF Abstract BibTeX arXiv:2412.15649

Code (1)

X-LANCE/SLAM-LLM 공식 구현 pytorch

Tasks

Spoken Dialogue Systems

Similar Papers 제목 키워드 기반

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

2025-09-29 · Chengyao Wang, Zhisheng Zhong, Bohao Peng, Senqiao Yang 외 arxiv

We present MGM-Omni, a unified Omni LLM for omni-modal understanding and expressive, long-horizon speech generation. Unlike cascaded pipelines that isolate speech synthesis, MGM-Omni adopts a "brain-mouth" design with a …

Multimodal ReasoningSpeech Synthesis

DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation

2026-02-12 · Xu Guo, Fulong Ye, Qichao Sun, Liyang Chen 외 arxiv

Recent advancements in foundation models have revolutionized joint audio-video generation. However, existing approaches typically treat human-centric tasks including reference-based audio-video generation (R2AV), video e…

Video Generation

Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement

2025-02-11 · Xueyao Zhang, Xiaohui Zhang, Kainan Peng, Zhenyu Tang 외

The imitation of voice, targeted on specific speech attributes such as timbre and speaking style, is crucial in speech generation. However, existing methods rely heavily on annotated data, and struggle with effectively d…

Disentanglementtext-to-speechText to SpeechVoice Conversion

Description-based Controllable Text-to-Speech with Cross-Lingual Voice Control

2024-09-26 · Ryuichi Yamamoto, Yuma Shirahata, Masaya Kawamura, Kentaro Tachibana

We propose a novel description-based controllable text-to-speech (TTS) method with cross-lingual control capability. To address the lack of audio-description paired data in the target language, we combine a TTS model tra…

Self-Supervised Learningtext-to-speechText to Speech

MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions

2025-07-14 · Ramaneswaran Selvakumar, Ashish Seth, Nishit Anand, Utkarsh Tyagi 외 arxiv

The rapid progress of Large Language Models (LLMs) has empowered omni models to act as voice assistants capable of understanding spoken dialogues. These models can process multimodal inputs beyond text, such as speech an…